© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44023
    Prev
    Next
    INDEX
    Explanations

    many

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     of
    -1.02
     a
    -0.88
     are
    -0.70
     many
    -0.70
     Many
    -0.68
    of
    -0.66
    Many
    -0.65
     Of
    -0.63
    a
    -0.63
     an
    -0.61
    POSITIVE LOGITS
    DockStyle
    1.04
     propOrder
    1.01
    RenderAtEndOf
    1.01
    OGND
    1.00
    expandindo
    1.00
    Datuak
    0.98
     itſelf
    0.98
     castes
    0.98
    AndEndTag
    0.94
     ་་
    0.93
    Activations Density 0.186%

    No Known Activations